Meta: muse-image
2 benchmarks
Leaderboard position
#89
Overall rank (of 1121 models)
2324
Elo rating
2
Benchmarks
Top 7.9%
Percentile
In Meta (of 12 models)
Above: Nex AGI: Nex-N2 Pro #88
Below: Qwen: qwen3.7-plus #90
Benchmark highlights
Worst benchmark
TTI-AlphabetBench
94.04
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 2 benchmarks
1/2
50.0%
1/2
50.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| Google: gemini-3.1-flash-lite-image | 1 | 50.0% |
| reve: reve-2.0 | 1 | 50.0% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~99.2 | 50% | — |
| AIME 2025 | ~100 | 50% | — |
| AIME 2026 | ~99.2 | 50% | — |
| HMMT Feb 2026 | ~93.53 | 50% | — |
| GPQA Diamond | ~90.42 | 50% | — |
| MMLU-Pro | ~90.53 | 50% | — |
| Humanity's Last Exam (no tools) | ~37.78 | 50% | — |
| IFEval | ~96.75 | 50% | — |
| IFBench | ~77.66 | 50% | — |
| HumanEval | ~95.9 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~72.44 | 50% | — |
| MMLU | ~92.5 | 50% | — |
| SWE-bench Verified | ~85.3 | 50% | — |
| SWE-bench Pro | ~61.13 | 50% | — |
| SciCode | ~49.88 | 50% | — |
| AA-LCR | ~71.81 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~25.02 | 50% | — |
| Humanity's Last Exam (with tools) | ~50.78 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~89.5 | 50% | — |
| MMMU-Pro | ~80.54 | 50% | — |
| MATH | ~97.9 | 50% | — |
| BBH | ~88.4 | 50% | — |